Rename app.py to app_toc.py

app.py → app_toc.py

@@ -20,24 +20,16 @@ from sklearn.metrics import mean_squared_error  # MAE removed
 # =========================
 # Constants / Defaults
 # =========================
-APP_NAME = "ST_GeoMech_UCS"
-TAGLINE  = "Real-Time Unconfined Compressive Strength Tracking While Drilling"
-
-# Default features standardized to match Ts/Tc apps.
-# (Older headers are still accepted via alias map below.)
-FEATURES = [
-    "WOB (klbf)",
-    "Torque (kft.lbf)",
-    "SPP (psi)",
-    "RPM (1/min)",
-    "ROP (ft/h)",
-    "Flow Rate (gpm)",
-]
-TARGET    = "UCS"
-PRED_COL  = "UCS_Pred"
+APP_NAME = "ST_GeoMech_TOC"
+TAGLINE  = "Real-Time Total Organic Carbon Estimation While Drilling"
+
+FEATURES = ["AHT90", "DT", "GR", "K", "RHOB", "TNPH", "Th", "Ur"]
+TARGET    = "TOC"
+PRED_COL  = "TOC_Pred"
 
 MODELS_DIR = Path("models")
-DEFAULT_MODEL = MODELS_DIR / "ucs_rf.joblib"
+DEFAULT_MODEL = MODELS_DIR / "toc_rf.joblib"   # <— point to your TOC model
+
 MODEL_FALLBACKS = [MODELS_DIR / "model.joblib", MODELS_DIR / "model.pkl"]
 COLORS = {"pred": "#1f77b4", "actual": "#f2b702", "ref": "#5a5a5a"}
 
@@ -165,42 +157,40 @@ def read_book_bytes(b: bytes):
 
 # ---- Canonical feature aliasing (accept legacy headers) ----
 def _build_alias_map(canonical_features: list[str], target_name: str) -> dict:
-    """
-    Map common header variants -> canonical names (from meta FEATURES).
-    """
-    def pick(expected_list, variants):
+    def pick(expected, variants):
         for v in variants:
-            if v in expected_list:
-                return v
+            if v in expected: return v
         return variants[0]
 
-    can_WOB    = pick(canonical_features, ["WOB (klbf)", "WOB, klbf", "WOB(klbf)", "WOB( klbf)"])
-    can_TORQUE = pick(canonical_features, ["Torque (kft.lbf)", "Torque(kft.lbf)", "T (kft.lbf)", "TORQUE(kft.lbf)"])
-    can_SPP    = pick(canonical_features, ["SPP (psi)", "SPP(psi)"])
-    can_RPM    = pick(canonical_features, ["RPM (1/min)", "RPM(1/min)"])
-    can_ROP    = pick(canonical_features, ["ROP (ft/h)", "ROP(ft/h)"])
-    can_FR     = pick(canonical_features, ["Flow Rate (gpm)", "Q, gpm", "Flow Rate, gpm", "Flow Rate,gpm", "Flow Rate , gpm"])
-    can_DEPTH  = "Depth (ft)"
+    # TOC logs/features
+    can_GR   = pick(canonical_features, ["GR", "Gamma Ray", "GR (API)"])
+    can_RHOB = pick(canonical_features, ["RHOB", "Bulk Density", "RHOB (g/cc)"])
+    can_DT   = pick(canonical_features, ["DT", "AC", "DT (us/ft)"])
+    can_TNPH = pick(canonical_features, ["TNPH", "NPHI", "TNPH (%)"])
+    can_K    = pick(canonical_features, ["K", "Potassium", "K (%)"])
+    can_Th   = pick(canonical_features, ["Th", "Thorium", "Th (ppm)"])
+    can_Ur   = pick(canonical_features, ["Ur", "U", "U (ppm)"])
+    can_AHT  = pick(canonical_features, ["AHT90", "AHT_90", "AHT-90"])
 
     alias = {
-        # Features
-        "WOB (klbf)": can_WOB, "WOB, klbf": can_WOB, "WOB(klbf)": can_WOB, "WOB( klbf)": can_WOB,
-        "Torque (kft.lbf)": can_TORQUE, "Torque(kft.lbf)": can_TORQUE, "T (kft.lbf)": can_TORQUE, "TORQUE(kft.lbf)": can_TORQUE,
-        "SPP (psi)": can_SPP, "SPP(psi)": can_SPP,
-        "RPM (1/min)": can_RPM, "RPM(1/min)": can_RPM,
-        "ROP (ft/h)": can_ROP, "ROP(ft/h)": can_ROP,
-        "Flow Rate (gpm)": can_FR, "Q, gpm": can_FR, "Flow Rate, gpm": can_FR, "Flow Rate,gpm": can_FR, "Flow Rate , gpm": can_FR,
-
-        # Depth (plot only)
-        "Depth (ft)": can_DEPTH, "Depth, ft": can_DEPTH, "Depth(ft)": can_DEPTH, "DEPTH, ft": can_DEPTH,
-
-        # Target aliases
-        "UCS": target_name,
-        "UCS (psi)": target_name,
-        "UCS_Actual": target_name,
+        "GR": can_GR, "Gamma Ray": can_GR, "GR (API)": can_GR,
+        "RHOB": can_RHOB, "Bulk Density": can_RHOB, "RHOB (g/cc)": can_RHOB,
+        "DT": can_DT, "AC": can_DT, "DT (us/ft)": can_DT,
+        "TNPH": can_TNPH, "NPHI": can_TNPH, "TNPH (%)": can_TNPH,
+        "K": can_K, "Potassium": can_K, "K (%)": can_K,
+        "Th": can_Th, "Thorium": can_Th, "Th (ppm)": can_Th,
+        "Ur": can_Ur, "U": can_Ur, "U (ppm)": can_Ur,
+        "AHT90": can_AHT, "AHT_90": can_AHT, "AHT-90": can_AHT,
+
+        # Optional depth for tracks
+        "Depth (ft)": "Depth (ft)", "DEPTH": "Depth (ft)", "MD (ft)": "Depth (ft)",
+
+        # Targets
+        "TOC": target_name, "TOC (%)": target_name, "Total Organic Carbon": target_name,
     }
     return alias
 
+
 def _normalize_columns(df: pd.DataFrame, canonical_features: list[str], target_name: str) -> pd.DataFrame:
     out = df.copy()
     out.columns = [str(c).strip().replace(" ,", ",").replace(",  ", ", ").replace("  ", " ") for c in out.columns]
@@ -368,7 +358,7 @@ def build_export_workbook(selected: list[str] | None = None) -> tuple[bytes|None
             df.to_excel(writer, sheet_name=_excel_safe_name(name), index=False)
     bio.seek(0)
 
-    fname = f"UCS_Export_{datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx"
+    fname = f"TOC_Export_{datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx"
     return bio.getvalue(), fname, order
 
 def render_export_button(phase_key: str) -> None:
@@ -405,7 +395,7 @@ def render_export_button(phase_key: str) -> None:
     st.download_button(
         "⬇️ Export Excel",
         data=(data or b""),
-        file_name=(fname or "UCS_Export.xlsx"),
+        file_name=(fname or "TOC_Export.xlsx"),
         mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
         disabled=(data is None),
         key=f"download_{phase_key}",
@@ -437,8 +427,8 @@ def cross_plot_static(actual, pred):
     fmt = FuncFormatter(lambda x, _: f"{x:,.0f}")
     ax.xaxis.set_major_formatter(fmt); ax.yaxis.set_major_formatter(fmt)
 
-    ax.set_xlabel("Actual UCS (psi)",    fontweight="bold", fontsize=10, color="black")
-    ax.set_ylabel("Predicted UCS (psi)", fontweight="bold", fontsize=10, color="black")
+    ax.set_xlabel("Actual TOC (%)",    fontweight="bold", fontsize=10, color="black")
+    ax.set_ylabel("Predicted TOC (%)", fontweight="bold", fontsize=10, color="black")
     ax.tick_params(labelsize=6, colors="black")
 
     ax.grid(True, linestyle=":", alpha=0.3)
@@ -492,9 +482,9 @@ def track_plot(df, include_actual=True):
         legend=dict(x=0.98, y=0.05, xanchor="right", yanchor="bottom",
                     bgcolor="rgba(255,255,255,0.75)", bordercolor="#ccc", borderwidth=1),
         legend_title_text=""
-    )
+    )  
     fig.update_xaxes(
-        title_text="UCS (psi)",
+        title_text="TOC (%)",
         title_font=dict(size=20, family=BOLD_FONT, color="#000"),
         tickfont=dict(size=12, family=BOLD_FONT, color="#000"),
         side="top", range=[xmin, xmax],
@@ -588,7 +578,7 @@ except Exception as e:
 
 # Prefer UCS-specific meta
 meta = {}
-meta_candidates = [MODELS_DIR / "ucs_meta.json", MODELS_DIR / "meta.json"]
+meta_candidates = [MODELS_DIR / "toc_meta.json", MODELS_DIR / "meta.json"]
 meta_path = next((p for p in meta_candidates if p.exists()), None)
 if meta_path:
     try: